Forensics Adapter: Unleashing CLIP for Generalizable Face Forgery Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-10 · 48 (10) · 13354-13369
DOI: 10.1109/tpami.2026.3706492 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-10. Verfasst von Xinjie Cui und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 83 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shandong Natural Science Foundation.
Abstract (Originalsprache)
We describe Forensics Adapter, an adapter network designed to transform CLIP into an effective and generalizable face forgery detector. Although CLIP is highly versatile, adapting it for face forgery detection is non-trivial as forgery-related knowledge is entangled with a wide range of unrelated knowledge. Existing methods treat CLIP merely as a feature extractor, lacking task-specific adaptation, which limits their effectiveness. To address this, we introduce an adapter to learn face forgery traces - the blending boundaries unique to forged faces, guided by task-specific objectives. Then we enhance the CLIP visual tokens with a dedicated interaction strategy that communicates knowledge across CLIP and the adapter. Since the adapter is alongside CLIP, its versatility is highly retained, naturally ensuring strong generalizability in face forgery detection. With only $ \boldsymbol {5.7M}$5.7M trainable parameters, our method achieves superior performance across six standard datasets. Additionally, we describe Forensics Adapter++, an extended method that incorporates textual modality via a newly proposed forgery-aware prompt learning strategy. This extension leads to a further $\boldsymbol {1.3\%}$1.3% performance boost over the original Forensics Adapter. We believe the proposed methods can serve as a baseline for future CLIP-based face forgery detection methods.
Förderung
- National Natural Science Foundation of China
- Shandong Natural Science Foundation
Zitieren
APA
Cui, X., Li, Y., Zhu, D., Zhou, J., Dong, J., & Lyu, S. (2026). Forensics Adapter: Unleashing CLIP for Generalizable Face Forgery Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(10), 13354-13369. https://doi.org/10.1109/tpami.2026.3706492
Vancouver
Cui X, Li Y, Zhu D, Zhou J, Dong J, Lyu S. Forensics Adapter: Unleashing CLIP for Generalizable Face Forgery Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(10):13354-13369. doi:10.1109/tpami.2026.3706492
BibTeX
@article{Cui2026,
author = {Cui, Xinjie and Li, Yuezun and Zhu, Delong and Zhou, Jiaran and Dong, Junyu and Lyu, Siwei},
title = {Forensics Adapter: Unleashing CLIP for Generalizable Face Forgery Detection},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {48},
number = {10},
pages = {13354--13369},
doi = {10.1109/tpami.2026.3706492}
}
EUVIMED